self-critical - Story 127393 | Emotion Vectors in Gemma4-31B

The library's silence amplified Amelia's unease. She'd picked up a well-loved copy of "Pride and Prejudice," seeking escape. A slip of paper fell out as she neared the end. It was a note, folded neatly, a child's shaky handwriting.

“Dear Grandma,” it began, describing a scraped knee and a missed school performance. The child's simple words about feeling like she’d disappointed someone stirred something within Amelia. It was a familiar ache, that feeling. She immediately thought of her own childhood, her parents' silent disapproval.

Amelia’s chest tightened as she read the child's last sentence, describing how she knew her grandma still loved her anyway. She pressed her lips together, her fingernails digging into the worn cover. She was far from a loving grandma to anyone, not even herself.

Emotion: self-critical

Cluster: Shame / Guilt

PC1 (Valence): -1.66 Negative

PC2 (Disposition): 1.28

Role in Research

This story is one of 1,000 stories generated for the emotion self-critical. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-critical stories, after denoising with neutral dialogue baselines, produces the self-critical emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:

`L`	0.748
`S`	0.662
`ness`	0.425
`ly`	0.374
`탓`	0.351

Suppressed:

`la`	-0.492
`soon`	-0.304
`(!)`	-0.301
`secured`	-0.284
`cautiously`	-0.280